{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:46T62LQDKOFOVPD5ITCON7NTUY","short_pith_number":"pith:46T62LQD","canonical_record":{"source":{"id":"1602.06346","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-19T23:46:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e5720cdc47b9e67281bf8d824e05531b7c3b9d64e3db30bf31470e95d4cebfd7","abstract_canon_sha256":"34b4ac6d2f10b9b87b2c26997fb1f7b4228ec35ec008be6a3bf3a9704e2e2425"},"schema_version":"1.0"},"canonical_sha256":"e7a7ed2e03538aeabc7d44c4e6fdb3a61eb7783ab7bff7810f967e7cf3b6606e","source":{"kind":"arxiv","id":"1602.06346","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.06346","created_at":"2026-05-18T01:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"1602.06346v2","created_at":"2026-05-18T01:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06346","created_at":"2026-05-18T01:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"46T62LQDKOFO","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"46T62LQDKOFOVPD5","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"46T62LQD","created_at":"2026-05-18T12:29:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:46T62LQDKOFOVPD5ITCON7NTUY","target":"record","payload":{"canonical_record":{"source":{"id":"1602.06346","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-19T23:46:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e5720cdc47b9e67281bf8d824e05531b7c3b9d64e3db30bf31470e95d4cebfd7","abstract_canon_sha256":"34b4ac6d2f10b9b87b2c26997fb1f7b4228ec35ec008be6a3bf3a9704e2e2425"},"schema_version":"1.0"},"canonical_sha256":"e7a7ed2e03538aeabc7d44c4e6fdb3a61eb7783ab7bff7810f967e7cf3b6606e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:09.213546Z","signature_b64":"gm1DAJw1CDxYW5Rx95MVLo2Mrpz1GAZRFvHSfo9b8ZPmy5KorZvAJDKCH2rs6h4DLUfO4Tp1SJRC8auoWgmZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7a7ed2e03538aeabc7d44c4e6fdb3a61eb7783ab7bff7810f967e7cf3b6606e","last_reissued_at":"2026-05-18T01:04:09.213036Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:09.213036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.06346","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:04:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YfnzhDjdlfrxBYfhzTJEy9YtLV9A5JcWBoXp1dX52f+VHFcuUHHY6XaRVFIfj668NLEy42Ao6Azinq/tOq1HBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:08:30.676296Z"},"content_sha256":"f6d6fd08f2510a7575408dcd309522cd6731384667bc8d4140529e634cfbfa54","schema_version":"1.0","event_id":"sha256:f6d6fd08f2510a7575408dcd309522cd6731384667bc8d4140529e634cfbfa54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:46T62LQDKOFOVPD5ITCON7NTUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernardo \\'Avila Pires, Csaba Szepesv\\'ari","submitted_at":"2016-02-19T23:46:11Z","abstract_excerpt":"In this paper we study a model-based approach to calculating approximately optimal policies in Markovian Decision Processes. In particular, we derive novel bounds on the loss of using a policy derived from a factored linear model, a class of models which generalize numerous previous models out of those that come with strong computational guarantees. For the first time in the literature, we derive performance bounds for model-based techniques where the model inaccuracy is measured in weighted norms. Moreover, our bounds show a decreased sensitivity to the discount factor and, unlike similar bou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06346","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:04:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rq10WK/WDQpzlvzX3/WjFqfktvHqQ6hODtzT9MHuuoeCF8DquYCV+8+DU1QjtKhZmCeKqD/HSnOYrvjhxRO9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:08:30.677029Z"},"content_sha256":"b7e3f5ea365968e02edfc024803ee9ebf4eb750dcecc593fed3c585740142835","schema_version":"1.0","event_id":"sha256:b7e3f5ea365968e02edfc024803ee9ebf4eb750dcecc593fed3c585740142835"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY/bundle.json","state_url":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/46T62LQDKOFOVPD5ITCON7NTUY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-06T20:08:30Z","links":{"resolver":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY","bundle":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY/bundle.json","state":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/46T62LQDKOFOVPD5ITCON7NTUY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:46T62LQDKOFOVPD5ITCON7NTUY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"34b4ac6d2f10b9b87b2c26997fb1f7b4228ec35ec008be6a3bf3a9704e2e2425","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-19T23:46:11Z","title_canon_sha256":"e5720cdc47b9e67281bf8d824e05531b7c3b9d64e3db30bf31470e95d4cebfd7"},"schema_version":"1.0","source":{"id":"1602.06346","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.06346","created_at":"2026-05-18T01:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"1602.06346v2","created_at":"2026-05-18T01:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06346","created_at":"2026-05-18T01:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"46T62LQDKOFO","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"46T62LQDKOFOVPD5","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"46T62LQD","created_at":"2026-05-18T12:29:58Z"}],"graph_snapshots":[{"event_id":"sha256:b7e3f5ea365968e02edfc024803ee9ebf4eb750dcecc593fed3c585740142835","target":"graph","created_at":"2026-05-18T01:04:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this paper we study a model-based approach to calculating approximately optimal policies in Markovian Decision Processes. In particular, we derive novel bounds on the loss of using a policy derived from a factored linear model, a class of models which generalize numerous previous models out of those that come with strong computational guarantees. For the first time in the literature, we derive performance bounds for model-based techniques where the model inaccuracy is measured in weighted norms. Moreover, our bounds show a decreased sensitivity to the discount factor and, unlike similar bou","authors_text":"Bernardo \\'Avila Pires, Csaba Szepesv\\'ari","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-19T23:46:11Z","title":"Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06346","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f6d6fd08f2510a7575408dcd309522cd6731384667bc8d4140529e634cfbfa54","target":"record","created_at":"2026-05-18T01:04:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"34b4ac6d2f10b9b87b2c26997fb1f7b4228ec35ec008be6a3bf3a9704e2e2425","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-19T23:46:11Z","title_canon_sha256":"e5720cdc47b9e67281bf8d824e05531b7c3b9d64e3db30bf31470e95d4cebfd7"},"schema_version":"1.0","source":{"id":"1602.06346","kind":"arxiv","version":2}},"canonical_sha256":"e7a7ed2e03538aeabc7d44c4e6fdb3a61eb7783ab7bff7810f967e7cf3b6606e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7a7ed2e03538aeabc7d44c4e6fdb3a61eb7783ab7bff7810f967e7cf3b6606e","first_computed_at":"2026-05-18T01:04:09.213036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:09.213036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gm1DAJw1CDxYW5Rx95MVLo2Mrpz1GAZRFvHSfo9b8ZPmy5KorZvAJDKCH2rs6h4DLUfO4Tp1SJRC8auoWgmZAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:09.213546Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.06346","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6d6fd08f2510a7575408dcd309522cd6731384667bc8d4140529e634cfbfa54","sha256:b7e3f5ea365968e02edfc024803ee9ebf4eb750dcecc593fed3c585740142835"],"state_sha256":"6f42b923d716450d1cce2cf18e264c64d04b77e5267ae03b66d66607c31f7b2d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cleK8U7mlCkg2xzJaNqJwFTqPX8Ok8K+K6MPjcwX2nArkpPU40OuGYUhTTy9kZYTYU/EOhVUDas73Z9GALCsCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T20:08:30.680794Z","bundle_sha256":"628666a26c02ee053ac401ba2d095e91ec8b6159692dec2c34cc19a81bb1f5cf"}}